Instructions to use abdoelsayed/llama-7b-v2-Receipt-Key-Extraction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abdoelsayed/llama-7b-v2-Receipt-Key-Extraction with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="abdoelsayed/llama-7b-v2-Receipt-Key-Extraction")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abdoelsayed/llama-7b-v2-Receipt-Key-Extraction")
model = AutoModelForCausalLM.from_pretrained("abdoelsayed/llama-7b-v2-Receipt-Key-Extraction")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use abdoelsayed/llama-7b-v2-Receipt-Key-Extraction with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abdoelsayed/llama-7b-v2-Receipt-Key-Extraction"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abdoelsayed/llama-7b-v2-Receipt-Key-Extraction",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/abdoelsayed/llama-7b-v2-Receipt-Key-Extraction

SGLang

How to use abdoelsayed/llama-7b-v2-Receipt-Key-Extraction with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "abdoelsayed/llama-7b-v2-Receipt-Key-Extraction" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abdoelsayed/llama-7b-v2-Receipt-Key-Extraction",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "abdoelsayed/llama-7b-v2-Receipt-Key-Extraction" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abdoelsayed/llama-7b-v2-Receipt-Key-Extraction",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use abdoelsayed/llama-7b-v2-Receipt-Key-Extraction with Docker Model Runner:
```
docker model run hf.co/abdoelsayed/llama-7b-v2-Receipt-Key-Extraction
```

abdoelsayed commited on Sep 22, 2023

Commit

f909dfc

1 Parent(s): 356c40c

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -25,7 +25,6 @@ Use the code below to get started with the model.
 ```bibtex
 # pip install -q transformers
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
@@ -64,6 +63,7 @@ response = generate_response(instruction, input_text)
 print(response)
 ```

 ```bibtex
 # pip install -q transformers
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
 print(response)
 ```